GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Runchuan Zhu, Xinke Jiang, Jiang Wu, Zhipeng Ma, Jiahe Song, Fengshuo Bai, Dahua Lin, Lijun Wu, Conghui He. GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation. In Luis Chiruzzo, Alan Ritter, Lu Wang, editors, Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29 - May 4, 2025. pages 4006-4021, Association for Computational Linguistics, 2025. [doi]

The following publications are possibly variants of this publication:

Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction TuningFuxiao Liu, Kevin Lin, Linjie Li, Jianfeng Wang, Yaser Yacoob, Lijuan Wang. iclr 2024: [doi]

Utilize the Flow Before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction TuningRunchuan Zhu, Zhipeng Ma, Jiang Wu, Junyuan Gao, Jiaqi Wang 0003, Dahua Lin, Conghui He. AAAI 2025: 26157-26165 [doi]

Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware PromptingJiarui Wu, Zhuo Liu, Hangfeng He 0001. naacl 2025: 3450-3468 [doi]

Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency AwareYujia Chen, Mingyu Chen, Cuiyun Gao, Zhihan Jiang, Zhongqi Li, Yuchi Ma. FSE 2025: 468-479 [doi]

RAG-HAT: A Hallucination-Aware Tuning Pipeline for LLM in Retrieval-Augmented GenerationJuntong Song, Xingguang Wang, Juno Zhu, Yuanhao Wu, Xuxin Cheng, Randy Zhong, Cheng Niu. emnlp 2024: 1548-1558 [doi]

Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption RewritesLei Wang 0185, Jiabang He, Shenshen Li, Ning Liu, Ee-Peng Lim. mmm 2024: 32-45 [doi]

runs on WebDSL